Road marking extraction in UAV imagery using attentive capsule feature pyramid network
•The proposed ACapsFPN extracted road markings in UAV images.•A capsule feature pyramid network provided a high-resolution, semantically-strong feature representation.•A novel multi-scale context feature (MCF) descriptor was designed to obtain multi-scale contextual information.•Ternary feature atte...
Saved in:
| Published in | International journal of applied earth observation and geoinformation Vol. 107; p. 102677 |
|---|---|
| Main Authors | , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.03.2022
Elsevier |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | •The proposed ACapsFPN extracted road markings in UAV images.•A capsule feature pyramid network provided a high-resolution, semantically-strong feature representation.•A novel multi-scale context feature (MCF) descriptor was designed to obtain multi-scale contextual information.•Ternary feature attention modules were designed to improve the accuracy of road marking extraction.
Accurately and precisely delineating road-markings from very high spatial resolution unmanned aerial vehicle (UAV) images face many challenges, such as complex scenarios, diverse road marking sizes and shapes, and absent and occluded road markings. To address these issues, we formulate an attentive capsule feature pyramid network (ACapsFPN) by integrating capsule representations with attention mechanisms into the feature pyramid network (FPN), aiming at improving road marking extraction accuracy. Different from the current convolutional neural network (CNN) models based on scalar neuron representations, capsule networks characterize entity features by leveraging vectorial capsule neurons, whose lengths and instantiation parameters contribute to the identification of features and their variants. By constructing a capsule FPN, the ACapsFPN is capable of extracting and integrating multi-level and multi-scale capsule features to provide high-quality and semantically-strong feature abstractions. By formulating a multi-scale context feature descriptor and the ternary feature attention modules, the ACapsFPN can emphasize informative features to generate a class-specific feature representation. Quantitative and qualitative evaluations show the ACapsFPN provides a valuable means for extracting road markings in UAV images under different kinds of complex conditions. In addition, comparative analyses with existing alternatives also demonstrate the superiority and robustness of the ACapsFPN in UAV road marking extraction. |
|---|---|
| AbstractList | Accurately and precisely delineating road-markings from very high spatial resolution unmanned aerial vehicle (UAV) images face many challenges, such as complex scenarios, diverse road marking sizes and shapes, and absent and occluded road markings. To address these issues, we formulate an attentive capsule feature pyramid network (ACapsFPN) by integrating capsule representations with attention mechanisms into the feature pyramid network (FPN), aiming at improving road marking extraction accuracy. Different from the current convolutional neural network (CNN) models based on scalar neuron representations, capsule networks characterize entity features by leveraging vectorial capsule neurons, whose lengths and instantiation parameters contribute to the identification of features and their variants. By constructing a capsule FPN, the ACapsFPN is capable of extracting and integrating multi-level and multi-scale capsule features to provide high-quality and semantically-strong feature abstractions. By formulating a multi-scale context feature descriptor and the ternary feature attention modules, the ACapsFPN can emphasize informative features to generate a class-specific feature representation. Quantitative and qualitative evaluations show the ACapsFPN provides a valuable means for extracting road markings in UAV images under different kinds of complex conditions. In addition, comparative analyses with existing alternatives also demonstrate the superiority and robustness of the ACapsFPN in UAV road marking extraction. •The proposed ACapsFPN extracted road markings in UAV images.•A capsule feature pyramid network provided a high-resolution, semantically-strong feature representation.•A novel multi-scale context feature (MCF) descriptor was designed to obtain multi-scale contextual information.•Ternary feature attention modules were designed to improve the accuracy of road marking extraction. Accurately and precisely delineating road-markings from very high spatial resolution unmanned aerial vehicle (UAV) images face many challenges, such as complex scenarios, diverse road marking sizes and shapes, and absent and occluded road markings. To address these issues, we formulate an attentive capsule feature pyramid network (ACapsFPN) by integrating capsule representations with attention mechanisms into the feature pyramid network (FPN), aiming at improving road marking extraction accuracy. Different from the current convolutional neural network (CNN) models based on scalar neuron representations, capsule networks characterize entity features by leveraging vectorial capsule neurons, whose lengths and instantiation parameters contribute to the identification of features and their variants. By constructing a capsule FPN, the ACapsFPN is capable of extracting and integrating multi-level and multi-scale capsule features to provide high-quality and semantically-strong feature abstractions. By formulating a multi-scale context feature descriptor and the ternary feature attention modules, the ACapsFPN can emphasize informative features to generate a class-specific feature representation. Quantitative and qualitative evaluations show the ACapsFPN provides a valuable means for extracting road markings in UAV images under different kinds of complex conditions. In addition, comparative analyses with existing alternatives also demonstrate the superiority and robustness of the ACapsFPN in UAV road marking extraction. |
| ArticleNumber | 102677 |
| Author | Guan, Haiyan Peng, Daifeng Marcato Junior, José Lei, Xiangda Yu, Yongtao Li, Jonathan Zhao, Haohao |
| Author_xml | – sequence: 1 givenname: Haiyan surname: Guan fullname: Guan, Haiyan email: guanhy.nj@nuist.edu.cn organization: School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China – sequence: 2 givenname: Xiangda surname: Lei fullname: Lei, Xiangda organization: School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China – sequence: 3 givenname: Yongtao surname: Yu fullname: Yu, Yongtao organization: Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223003, China – sequence: 4 givenname: Haohao surname: Zhao fullname: Zhao, Haohao organization: School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China – sequence: 5 givenname: Daifeng surname: Peng fullname: Peng, Daifeng organization: School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China – sequence: 6 givenname: José surname: Marcato Junior fullname: Marcato Junior, José organization: Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070900, Brazil – sequence: 7 givenname: Jonathan surname: Li fullname: Li, Jonathan organization: Department of Geography and Environmental Management and Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada |
| BookMark | eNp9kU1v1DAQhiNUJNrCD-DmI5cs8cfajjhVFR-VKiEhWnGzxs545TQbL7bTsv8eL4ELh5489szzavy-F83ZHGdsmre029COyvfjZoTdhnWM1TuTSr1ozqlWrNVM_jir9Vb2rRacvWouch67jiol9Xlz_y3CQPaQHsK8I_irJHAlxJmEmdxd3ZOwhx2mI1nyqQ-l4FzCIxIHh7xMSDxCWRKSwzHBPgxkxvIU08Pr5qWHKeObv-dlc_fp4_frL-3t188311e3rRO8L62lvvMoUFrNGCAfGAys6xG95brnPXjoewtK0AGZld7KobfCbjX3naogv2xuVt0hwmgOqa6bjiZCMH8eYtoZSCW4CY3V3oHsrXRKCFG1wPZOKI6D1I4rWrXerVqHFH8umIvZh-xwmmDGuGTDFNWMC7nt6qhaR12KOSf0xoUCJ9-qf2EytDOnVMxoairmlIpZU6kk_Y_8t_RzzIeVwerkY8Bksgs4OxxCQlfqV8Mz9G_0h6ji |
| CitedBy_id | crossref_primary_10_1080_10106049_2024_2364679 crossref_primary_10_1080_19479832_2024_2382737 crossref_primary_10_3389_fpls_2023_1103276 crossref_primary_10_1109_TGRS_2024_3495508 crossref_primary_10_1016_j_jag_2022_102851 |
| Cites_doi | 10.1109/TGRS.2020.3016086 10.1109/TITS.2020.2990120 10.1016/j.neucom.2017.09.098 10.1109/TPAMI.2020.2983686 10.1016/j.eswa.2014.10.024 10.1109/TITS.2015.2393715 10.5220/0005273501300138 10.1109/TNNLS.2016.2522428 10.1109/ACCESS.2019.2933598 10.1109/TIV.2018.2873902 10.1016/j.patcog.2015.12.010 10.1016/j.isprsjprs.2021.01.025 10.1109/ICCV.2017.215 10.1109/TGRS.2018.2878510 10.1109/TITS.2006.869595 10.1109/TITS.2015.2438714 10.1109/TITS.2018.2791572 10.1016/j.isprsjprs.2020.05.009 10.1109/TITS.2007.908582 10.1109/TITS.2012.2184756 10.1016/j.isprsjprs.2007.10.005 10.1109/TITS.2015.2464253 10.1109/TGRS.2018.2871782 10.1016/j.measurement.2018.07.089 10.1109/TITS.2020.2983077 10.1080/01431161.2020.1842544 10.1109/TGRS.2020.2996617 10.1155/2018/9106836 10.1109/JSTARS.2015.2495142 10.1016/j.isprsjprs.2018.10.007 10.1109/TITS.2020.2984813 10.1109/TITS.2016.2586187 10.1109/CVPR.2017.106 |
| ContentType | Journal Article |
| Copyright | 2022 The Author(s) |
| Copyright_xml | – notice: 2022 The Author(s) |
| DBID | 6I. AAFTH AAYXX CITATION 7S9 L.6 DOA |
| DOI | 10.1016/j.jag.2022.102677 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef AGRICOLA AGRICOLA - Academic DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ - Directory of Open Access Journals (Some content may be blocked by TCTC IT security protocols) url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Environmental Sciences |
| EISSN | 1872-826X |
| ExternalDocumentID | oai_doaj_org_article_b8fca69b6c74446fbab9c473ed68c371 10_1016_j_jag_2022_102677 S0303243422000034 |
| GroupedDBID | 29J 4.4 5GY 6I. AAFTH AAQXK AAXUO ABFYP ABLST ABQEM ABQYD ABYKQ ACLVX ACRLP ACSBN ADBBV ADMUD AFKWA AFTJW AFXIZ AGYEJ AHEUO AIKHN AJBFU AJOXV AKIFW ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ASPBG ATOGT AVWKF AZFZN BKOJK BLECG EBS EJD FDB FEDTE FIRID FYGXN GROUPED_DOAJ HVGLF IMUCA KCYFY KOM M41 O-L P-8 P-9 P2P R2- RIG ROL SDF SDG SES SPC SSE SSJ T5K ~02 AAHBH AALRI AATTM AAXKI AAYWO AAYXX ABJNI ABWVN ACRPL ADNMO ADVLN AEIPS AFJKZ AGCQF AGQPQ AGRNS AIIUN AITUG ANKPU APXCP BNPGV CITATION EFJIC SSH 7S9 L.6 EFKBS |
| ID | FETCH-LOGICAL-c439t-b1f0fe4e6b822ae3d2ad209eefb38939afa99ba741de2b6fb6d9b4b583f07fe43 |
| IEDL.DBID | DOA |
| ISSN | 1569-8432 |
| IngestDate | Wed Aug 27 01:29:31 EDT 2025 Fri Jul 11 11:34:11 EDT 2025 Tue Jul 01 02:15:19 EDT 2025 Thu Apr 24 23:11:39 EDT 2025 Fri Feb 23 02:40:01 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Road markings Capsule Dense atrous convolution Feature pyramid network UAV images |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c439t-b1f0fe4e6b822ae3d2ad209eefb38939afa99ba741de2b6fb6d9b4b583f07fe43 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://doaj.org/article/b8fca69b6c74446fbab9c473ed68c371 |
| PQID | 2718234650 |
| PQPubID | 24069 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_b8fca69b6c74446fbab9c473ed68c371 proquest_miscellaneous_2718234650 crossref_citationtrail_10_1016_j_jag_2022_102677 crossref_primary_10_1016_j_jag_2022_102677 elsevier_sciencedirect_doi_10_1016_j_jag_2022_102677 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | March 2022 2022-03-00 20220301 2022-03-01 |
| PublicationDateYYYYMMDD | 2022-03-01 |
| PublicationDate_xml | – month: 03 year: 2022 text: March 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | International journal of applied earth observation and geoinformation |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | Hu, Shen, Sun (b0080) 2018; 2018 Xiao, Yang, Li, Islam (b0210) 2020; 194 Wen, Sun, Li, Wang, Guo, Habib (b0205) 2019; 147 Girshick, Donahue, Darrell, Malik (b0035) 2014; 2014 Wang, Sun, Cheng, Jiang, Deng, Zhao, Liu, Mu, Tan, Wang, Liu, Xiao (b0200) 2021; 43 Huang, Liu, van der Maaten, Weinberger (b0085) 2017; 2017 Gopalan, Hong, Shneier, Chellappa (b0045) 2012; 13 Hoang, Nam, Park (b0075) 2019; 7 Shamsolmoali, Zareapoor, Zhou, Wang, Yang (b0185) 2021; 59 Ma, Li, Li, Yu, Junior, Goncalves, Chapman (b0130) 2021; 22 Ma, Zhong, Li, Ma, Cui, Wang (b0135) 2021; 22 Prakash, Comandur, Chang, Elfiky, Kak (b0165) 2015; 8 Zhao, Shi, Qi, Wang, Jia (b0235) 2017; 2017 Girshick (b0040) 2015; 2015 Zhu, Huang, Hu, Li, Chen, Zhong (b0240) 2021; 174 Chen, L., Papandreou, G., Schroff, F., Adam, H., 2017. Rethinking atrous convolution for semantic image segmentation. CoRR, vol. abs/1706.05587, 2017. [Online]. Available Ozgunalp, Fan, Ai, Dahnoun (b0155) 2017; 18 Yu, Yao, Guan, Li, Liu, Wang, Yu, Xiao, Wang, Chang (b0225) 2021; 42 McCall, Trivedi (b0145) 2006; 7 Shamsolmoali, Chanussot, Zareapoor, Zhou, Yang (b0175) 2021 Gupta, Choudhary (b0060) 2018; 3 Niu, Lu, Xu, Lv, Zhao (b0150) 2016; 59 Kim (b0095) 2008; 9 Grabner, Nguyen, Gruber, Bischof (b0050) 2008; 63 Lee, Moon (b0100) 2018; 19 Mathibela, Newman, Posner (b0140) 2015; 16 Chen, Zhang, Zhong, Zhang, Ma, Liu (b0020) 2021; 59 Lee, S., Kim, J., Yoon, J. S., Shin, S., Bailo, O., Kim, N., Lee, T.-H., Hong, H. S., Han, S.-H., Kweon, I. S., 2017. VPGNet: Vanishing point guided network for lane and road marking detection and recognition. In: Proc. IEEE Int. Conf. Comput. Vis., Venice, Italy, Oct. 2017, pp. 1965–1973. Paoletti, Haut, Fernandez-Beltran, Plaza, Plaza, Li, Pla (b0160) 2019; 57 Sabour, S., Frosst, N., Hinton, G.E., 2017. Dynamic routing between capsules. In: Proc. 31st Conference on Neural Information Processing Systems, Long Beach, CA, USA, 4–10 Dec. 2017, pp. 1–11. Azimi, Fischer, Korner, Reinartz (b0005) 2019; 57 . Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S., 2017. Feature pyramid networks for object detection. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 2117–2125. Zhang, Wang, Yang, Qiang Li, Chen, Qiu (b0230) 2018; 130 de Paula, Jung (b0010) 2015; 16 Son, Yoo, Kim, Sohn (b0190) 2015; 42 Greenhalgh, Mirmehdi (b0055) 2015; 2015 Jung, Youn, Sull (b0090) 2016; 17 Lyu, Vosselman, Xia, Yilmaz, Yang (b0125) 2020; 165 Ye, Hong, Chen, Hsiao, Fu (b0220) 2020; 102 Han, Han, Hahn (b0065) 2009; 59 Shamsolmoali, Zareapoor, Chanussot, Zhou, Yang (b0180) 2021 Xu, Yu, Hu, Ng, Heng (b0215) 2021; 22 Li, Mei, Prokhorov, Tao (b0110) 2017; 28 Li, Li, Jiang (b0115) 2018; 2018 Tian, Gelernter, Wang, Chen, Gao, Zhang, Li (b0195) 2018; 280 He, B., Ai, R., Yan, Y., Lang, X., 2016. Accurate and robust lane detection based on dual-view convolutional neutral network. In: Proceedings of the IEEE Intell. Vehicles Symp., Gothenburg, Sweden, Jun. 2016, pp. 1041–1046. Chen, Wang, Peng, Zhang, Yu, Sun (b0025) 2018; 2018 Xu (10.1016/j.jag.2022.102677_b0215) 2021; 22 McCall (10.1016/j.jag.2022.102677_b0145) 2006; 7 Azimi (10.1016/j.jag.2022.102677_b0005) 2019; 57 Zhu (10.1016/j.jag.2022.102677_b0240) 2021; 174 Hoang (10.1016/j.jag.2022.102677_b0075) 2019; 7 Ma (10.1016/j.jag.2022.102677_b0135) 2021; 22 Grabner (10.1016/j.jag.2022.102677_b0050) 2008; 63 Xiao (10.1016/j.jag.2022.102677_b0210) 2020; 194 Ma (10.1016/j.jag.2022.102677_b0130) 2021; 22 Paoletti (10.1016/j.jag.2022.102677_b0160) 2019; 57 de Paula (10.1016/j.jag.2022.102677_b0010) 2015; 16 Zhang (10.1016/j.jag.2022.102677_b0230) 2018; 130 Prakash (10.1016/j.jag.2022.102677_b0165) 2015; 8 10.1016/j.jag.2022.102677_b0070 Son (10.1016/j.jag.2022.102677_b0190) 2015; 42 Yu (10.1016/j.jag.2022.102677_b0225) 2021; 42 Chen (10.1016/j.jag.2022.102677_b0025) 2018; 2018 10.1016/j.jag.2022.102677_b0170 10.1016/j.jag.2022.102677_b0015 Chen (10.1016/j.jag.2022.102677_b0020) 2021; 59 Greenhalgh (10.1016/j.jag.2022.102677_b0055) 2015; 2015 Ozgunalp (10.1016/j.jag.2022.102677_b0155) 2017; 18 Shamsolmoali (10.1016/j.jag.2022.102677_b0185) 2021; 59 Ye (10.1016/j.jag.2022.102677_b0220) 2020; 102 Han (10.1016/j.jag.2022.102677_b0065) 2009; 59 Niu (10.1016/j.jag.2022.102677_b0150) 2016; 59 Girshick (10.1016/j.jag.2022.102677_b0035) 2014; 2014 Li (10.1016/j.jag.2022.102677_b0115) 2018; 2018 Jung (10.1016/j.jag.2022.102677_b0090) 2016; 17 Li (10.1016/j.jag.2022.102677_b0110) 2017; 28 Mathibela (10.1016/j.jag.2022.102677_b0140) 2015; 16 Wen (10.1016/j.jag.2022.102677_b0205) 2019; 147 Lyu (10.1016/j.jag.2022.102677_b0125) 2020; 165 Tian (10.1016/j.jag.2022.102677_b0195) 2018; 280 Gupta (10.1016/j.jag.2022.102677_b0060) 2018; 3 Zhao (10.1016/j.jag.2022.102677_b0235) 2017; 2017 Kim (10.1016/j.jag.2022.102677_b0095) 2008; 9 Gopalan (10.1016/j.jag.2022.102677_b0045) 2012; 13 Girshick (10.1016/j.jag.2022.102677_b0040) 2015; 2015 10.1016/j.jag.2022.102677_b0120 Shamsolmoali (10.1016/j.jag.2022.102677_b0175) 2021 Shamsolmoali (10.1016/j.jag.2022.102677_b0180) 2021 Hu (10.1016/j.jag.2022.102677_b0080) 2018; 2018 Lee (10.1016/j.jag.2022.102677_b0100) 2018; 19 Wang (10.1016/j.jag.2022.102677_b0200) 2021; 43 10.1016/j.jag.2022.102677_b0105 Huang (10.1016/j.jag.2022.102677_b0085) 2017; 2017 |
| References_xml | – volume: 280 start-page: 46 year: 2018 end-page: 55 ident: b0195 article-title: Lane marking detection via deep convolutional neural network publication-title: Neurocomput. – volume: 28 start-page: 690 year: 2017 end-page: 703 ident: b0110 article-title: Deep neural network for structural prediction and lane detection in traffic scene publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 2018 start-page: 7103 year: 2018 end-page: 7112 ident: b0025 article-title: Cascaded pyramid network for multi-person pose estimation publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – year: 2021 ident: b0180 article-title: Rotation equivariant feature image pyramid network for object detection in optical remote sensing imagery publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 22 start-page: 4986 year: 2021 end-page: 4997 ident: b0215 article-title: SALMNet: a structure-aware lane marking detection network publication-title: IEEE Trans. Intell. Transport. Syst. – volume: 2015 start-page: 1440 year: 2015 end-page: 1448 ident: b0040 article-title: R-CNN Fast publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – volume: 3 start-page: 476 year: 2018 end-page: 485 ident: b0060 article-title: A framework for camera-based real-time lane and road surface marking detection and recognition publication-title: IEEE Trans. Intell. Vehicles – reference: He, B., Ai, R., Yan, Y., Lang, X., 2016. Accurate and robust lane detection based on dual-view convolutional neutral network. In: Proceedings of the IEEE Intell. Vehicles Symp., Gothenburg, Sweden, Jun. 2016, pp. 1041–1046. – volume: 22 start-page: 1981 year: 2021 end-page: 1995 ident: b0130 article-title: Capsule-based networks for road marking extraction and classification from mobile LiDAR point clouds publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 19 start-page: 4043 year: 2018 end-page: 4048 ident: b0100 article-title: Robust lane detection and tracking for real-time applications publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 2014 start-page: 580 year: 2014 end-page: 587 ident: b0035 article-title: Rich feature hierarchies for accurate object detection and semantic segmentation publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – volume: 57 start-page: 2145 year: 2019 end-page: 2160 ident: b0160 article-title: Capsule networks for hyperspectral image classification publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 59 start-page: 4673 year: 2021 end-page: 4688 ident: b0185 article-title: Road segmentation for remote sensing images using adversarial spatial pyramid networks publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 130 start-page: 105 year: 2018 end-page: 117 ident: b0230 article-title: Pavement lane marking detection using matched filter publication-title: Measurement – volume: 43 start-page: 3349 year: 2021 end-page: 3364 ident: b0200 article-title: Deep high-resolution representation learning for visual recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 2018 start-page: 7132 year: 2018 end-page: 7141 ident: b0080 article-title: Squeeze-and-excitation networks publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – reference: Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S., 2017. Feature pyramid networks for object detection. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 2117–2125. – volume: 165 start-page: 108 year: 2020 end-page: 119 ident: b0125 article-title: UAVid: A semantic segmentation dataset for UAV imagery publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 42 start-page: 1816 year: 2015 end-page: 1824 ident: b0190 article-title: Real-time illumination invariant lane detection for lane departure warning system publication-title: Expert Syst. Appl. – reference: Chen, L., Papandreou, G., Schroff, F., Adam, H., 2017. Rethinking atrous convolution for semantic image segmentation. CoRR, vol. abs/1706.05587, 2017. [Online]. Available: – volume: 147 start-page: 178 year: 2019 end-page: 192 ident: b0205 article-title: A deep learning framework for road marking extraction, classification and completion from mobile laser scanning point clouds publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 2017 start-page: 2881 year: 2017 end-page: 2890 ident: b0235 article-title: Pyramid scene parsing network publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – reference: Lee, S., Kim, J., Yoon, J. S., Shin, S., Bailo, O., Kim, N., Lee, T.-H., Hong, H. S., Han, S.-H., Kweon, I. S., 2017. VPGNet: Vanishing point guided network for lane and road marking detection and recognition. In: Proc. IEEE Int. Conf. Comput. Vis., Venice, Italy, Oct. 2017, pp. 1965–1973. – volume: 63 start-page: 382 year: 2008 end-page: 396 ident: b0050 article-title: On-line boosting based car detection from aerial images publication-title: ISPRS J. Photogramm. Remote Sens. – reference: Sabour, S., Frosst, N., Hinton, G.E., 2017. Dynamic routing between capsules. In: Proc. 31st Conference on Neural Information Processing Systems, Long Beach, CA, USA, 4–10 Dec. 2017, pp. 1–11. – volume: 13 start-page: 1088 year: 2012 end-page: 1098 ident: b0045 article-title: A learning approach towards detection and tracking of lane markings publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 7 start-page: 20 year: 2006 end-page: 37 ident: b0145 article-title: Video-based lane estimation and tracking for driver assistance: Survey, system, and evaluation publication-title: IEEE Trans. Intell. Transp. Syst. – year: 2021 ident: b0175 article-title: Multipatch feature pyramid network for weakly supervised object detection in optical remote sensing images publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 9 start-page: 16 year: 2008 end-page: 26 ident: b0095 article-title: Robust lane detection and tracking in challenging scenarios publication-title: IEEE Trans. Intell. Transport. Syst. – volume: 16 start-page: 2072 year: 2015 end-page: 2081 ident: b0140 article-title: Reading the road: road marking classification and interpretation publication-title: IEEE Trans. Intell. Transport. Syst. – volume: 18 start-page: 621 year: 2017 end-page: 632 ident: b0155 article-title: Multiple lane detection algorithm based on novel dense vanishing point estimation publication-title: IEEE Trans. Intell. Transport. Syst. – volume: 2017 start-page: 4700 year: 2017 end-page: 4708 ident: b0085 article-title: Densely connected convolutional networks publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – volume: 59 start-page: 784 year: 2021 end-page: 800 ident: b0020 article-title: A dense feature pyramid network-based deep learning model for road marking instance segmentation using MLS point clouds publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 194 start-page: 1 year: 2020 end-page: 10 ident: b0210 article-title: Attention deep neural network for lane marking detection publication-title: Knowl-Based Syst. – reference: . – volume: 42 start-page: 1801 year: 2021 end-page: 1822 ident: b0225 article-title: A self-attention capsule feature pyramid network for water body extraction from remote sensing imagery publication-title: Int. J. Remote Sens. – volume: 7 start-page: 109817 year: 2019 end-page: 109832 ident: b0075 article-title: Enhanced detection and recognition of road markings based on adaptive region of interest and deep learning publication-title: IEEE Access – volume: 22 start-page: 4813 year: 2021 end-page: 4824 ident: b0135 article-title: Forecasting transportation network speed using deep capsule networks with nested LSTM models publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 2018 start-page: 1 year: 2018 end-page: 13 ident: b0115 article-title: Lane detection based on connection of various feature extraction methods publication-title: Adv. Multimedia – volume: 16 start-page: 3160 year: 2015 end-page: 3169 ident: b0010 article-title: Automatic detection and classification of road lane markings using onboard vehicular cameras publication-title: IEEE Trans. Intell. Transport. Syst. – volume: 8 start-page: 4729 year: 2015 end-page: 4741 ident: b0165 article-title: A generic road-following framework for detecting markings and objects in satellite imagery publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. – volume: 174 start-page: 105 year: 2021 end-page: 116 ident: b0240 article-title: Depth-enhanced feature pyramid network for occlusion-aware verification of buildings from oblique images publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 2015 start-page: 130 year: 2015 end-page: 138 ident: b0055 article-title: Detection and recognition of painted road surface markings publication-title: Proc. Int. Conf. Pattern Recognit. Appl. Methods – volume: 57 start-page: 2920 year: 2019 end-page: 2938 ident: b0005 article-title: Aerial LaneNet: lane-marking semantic segmentation in aerial imagery using wavelet-enhanced cost-sensitive symmetric fully convolutional neural networks publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 17 start-page: 289 year: 2016 end-page: 295 ident: b0090 article-title: Efficient lane detection based on spatiotemporal images publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 102 start-page: 1 year: 2020 end-page: 11 ident: b0220 article-title: A two-stage real-time YOLOv2-based road marking detector with lightweight spatial transformation-invariant classification publication-title: Image Vis. Comput. – volume: 59 start-page: 225 year: 2016 end-page: 233 ident: b0150 article-title: Robust lane detection using two-stage feature extraction with curve fitting publication-title: Pattern Recognit. – volume: 59 start-page: 455 year: 2009 end-page: 459 ident: b0065 article-title: Vehicle detection method using Haar-like feature on real time system publication-title: World Acad. Sci. Eng. Technol. – volume: 2014 start-page: 580 year: 2014 ident: 10.1016/j.jag.2022.102677_b0035 article-title: Rich feature hierarchies for accurate object detection and semantic segmentation publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – volume: 59 start-page: 4673 issue: 6 year: 2021 ident: 10.1016/j.jag.2022.102677_b0185 article-title: Road segmentation for remote sensing images using adversarial spatial pyramid networks publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2020.3016086 – volume: 22 start-page: 1981 issue: 4 year: 2021 ident: 10.1016/j.jag.2022.102677_b0130 article-title: Capsule-based networks for road marking extraction and classification from mobile LiDAR point clouds publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2020.2990120 – year: 2021 ident: 10.1016/j.jag.2022.102677_b0180 article-title: Rotation equivariant feature image pyramid network for object detection in optical remote sensing imagery publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 280 start-page: 46 year: 2018 ident: 10.1016/j.jag.2022.102677_b0195 article-title: Lane marking detection via deep convolutional neural network publication-title: Neurocomput. doi: 10.1016/j.neucom.2017.09.098 – volume: 43 start-page: 3349 issue: 10 year: 2021 ident: 10.1016/j.jag.2022.102677_b0200 article-title: Deep high-resolution representation learning for visual recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.2983686 – ident: 10.1016/j.jag.2022.102677_b0070 – volume: 42 start-page: 1816 issue: 4 year: 2015 ident: 10.1016/j.jag.2022.102677_b0190 article-title: Real-time illumination invariant lane detection for lane departure warning system publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2014.10.024 – volume: 2018 start-page: 7103 year: 2018 ident: 10.1016/j.jag.2022.102677_b0025 article-title: Cascaded pyramid network for multi-person pose estimation publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – volume: 16 start-page: 2072 issue: 4 year: 2015 ident: 10.1016/j.jag.2022.102677_b0140 article-title: Reading the road: road marking classification and interpretation publication-title: IEEE Trans. Intell. Transport. Syst. doi: 10.1109/TITS.2015.2393715 – volume: 2015 start-page: 130 year: 2015 ident: 10.1016/j.jag.2022.102677_b0055 article-title: Detection and recognition of painted road surface markings publication-title: Proc. Int. Conf. Pattern Recognit. Appl. Methods doi: 10.5220/0005273501300138 – volume: 28 start-page: 690 issue: 3 year: 2017 ident: 10.1016/j.jag.2022.102677_b0110 article-title: Deep neural network for structural prediction and lane detection in traffic scene publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2016.2522428 – volume: 2017 start-page: 4700 year: 2017 ident: 10.1016/j.jag.2022.102677_b0085 article-title: Densely connected convolutional networks publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – volume: 7 start-page: 109817 year: 2019 ident: 10.1016/j.jag.2022.102677_b0075 article-title: Enhanced detection and recognition of road markings based on adaptive region of interest and deep learning publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2933598 – volume: 3 start-page: 476 issue: 4 year: 2018 ident: 10.1016/j.jag.2022.102677_b0060 article-title: A framework for camera-based real-time lane and road surface marking detection and recognition publication-title: IEEE Trans. Intell. Vehicles doi: 10.1109/TIV.2018.2873902 – volume: 59 start-page: 225 year: 2016 ident: 10.1016/j.jag.2022.102677_b0150 article-title: Robust lane detection using two-stage feature extraction with curve fitting publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2015.12.010 – volume: 174 start-page: 105 year: 2021 ident: 10.1016/j.jag.2022.102677_b0240 article-title: Depth-enhanced feature pyramid network for occlusion-aware verification of buildings from oblique images publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2021.01.025 – ident: 10.1016/j.jag.2022.102677_b0105 doi: 10.1109/ICCV.2017.215 – volume: 57 start-page: 2920 issue: 5 year: 2019 ident: 10.1016/j.jag.2022.102677_b0005 article-title: Aerial LaneNet: lane-marking semantic segmentation in aerial imagery using wavelet-enhanced cost-sensitive symmetric fully convolutional neural networks publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2018.2878510 – volume: 7 start-page: 20 issue: 1 year: 2006 ident: 10.1016/j.jag.2022.102677_b0145 article-title: Video-based lane estimation and tracking for driver assistance: Survey, system, and evaluation publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2006.869595 – volume: 16 start-page: 3160 issue: 6 year: 2015 ident: 10.1016/j.jag.2022.102677_b0010 article-title: Automatic detection and classification of road lane markings using onboard vehicular cameras publication-title: IEEE Trans. Intell. Transport. Syst. doi: 10.1109/TITS.2015.2438714 – volume: 19 start-page: 4043 issue: 12 year: 2018 ident: 10.1016/j.jag.2022.102677_b0100 article-title: Robust lane detection and tracking for real-time applications publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2018.2791572 – volume: 165 start-page: 108 year: 2020 ident: 10.1016/j.jag.2022.102677_b0125 article-title: UAVid: A semantic segmentation dataset for UAV imagery publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2020.05.009 – ident: 10.1016/j.jag.2022.102677_b0015 – volume: 9 start-page: 16 issue: 1 year: 2008 ident: 10.1016/j.jag.2022.102677_b0095 article-title: Robust lane detection and tracking in challenging scenarios publication-title: IEEE Trans. Intell. Transport. Syst. doi: 10.1109/TITS.2007.908582 – volume: 13 start-page: 1088 issue: 3 year: 2012 ident: 10.1016/j.jag.2022.102677_b0045 article-title: A learning approach towards detection and tracking of lane markings publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2012.2184756 – ident: 10.1016/j.jag.2022.102677_b0170 – volume: 63 start-page: 382 issue: 3 year: 2008 ident: 10.1016/j.jag.2022.102677_b0050 article-title: On-line boosting based car detection from aerial images publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2007.10.005 – volume: 102 start-page: 1 issue: 103978 year: 2020 ident: 10.1016/j.jag.2022.102677_b0220 article-title: A two-stage real-time YOLOv2-based road marking detector with lightweight spatial transformation-invariant classification publication-title: Image Vis. Comput. – volume: 17 start-page: 289 issue: 1 year: 2016 ident: 10.1016/j.jag.2022.102677_b0090 article-title: Efficient lane detection based on spatiotemporal images publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2015.2464253 – volume: 194 start-page: 1 issue: 105584 year: 2020 ident: 10.1016/j.jag.2022.102677_b0210 article-title: Attention deep neural network for lane marking detection publication-title: Knowl-Based Syst. – volume: 2015 start-page: 1440 year: 2015 ident: 10.1016/j.jag.2022.102677_b0040 article-title: R-CNN Fast publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – volume: 2018 start-page: 7132 year: 2018 ident: 10.1016/j.jag.2022.102677_b0080 article-title: Squeeze-and-excitation networks publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – volume: 57 start-page: 2145 issue: 4 year: 2019 ident: 10.1016/j.jag.2022.102677_b0160 article-title: Capsule networks for hyperspectral image classification publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2018.2871782 – volume: 130 start-page: 105 year: 2018 ident: 10.1016/j.jag.2022.102677_b0230 article-title: Pavement lane marking detection using matched filter publication-title: Measurement doi: 10.1016/j.measurement.2018.07.089 – volume: 22 start-page: 4986 issue: 8 year: 2021 ident: 10.1016/j.jag.2022.102677_b0215 article-title: SALMNet: a structure-aware lane marking detection network publication-title: IEEE Trans. Intell. Transport. Syst. doi: 10.1109/TITS.2020.2983077 – volume: 42 start-page: 1801 issue: 5 year: 2021 ident: 10.1016/j.jag.2022.102677_b0225 article-title: A self-attention capsule feature pyramid network for water body extraction from remote sensing imagery publication-title: Int. J. Remote Sens. doi: 10.1080/01431161.2020.1842544 – volume: 59 start-page: 784 issue: 1 year: 2021 ident: 10.1016/j.jag.2022.102677_b0020 article-title: A dense feature pyramid network-based deep learning model for road marking instance segmentation using MLS point clouds publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2020.2996617 – volume: 59 start-page: 455 year: 2009 ident: 10.1016/j.jag.2022.102677_b0065 article-title: Vehicle detection method using Haar-like feature on real time system publication-title: World Acad. Sci. Eng. Technol. – volume: 2018 start-page: 1 year: 2018 ident: 10.1016/j.jag.2022.102677_b0115 article-title: Lane detection based on connection of various feature extraction methods publication-title: Adv. Multimedia doi: 10.1155/2018/9106836 – year: 2021 ident: 10.1016/j.jag.2022.102677_b0175 article-title: Multipatch feature pyramid network for weakly supervised object detection in optical remote sensing images publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 8 start-page: 4729 issue: 10 year: 2015 ident: 10.1016/j.jag.2022.102677_b0165 article-title: A generic road-following framework for detecting markings and objects in satellite imagery publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2015.2495142 – volume: 147 start-page: 178 year: 2019 ident: 10.1016/j.jag.2022.102677_b0205 article-title: A deep learning framework for road marking extraction, classification and completion from mobile laser scanning point clouds publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2018.10.007 – volume: 22 start-page: 4813 issue: 8 year: 2021 ident: 10.1016/j.jag.2022.102677_b0135 article-title: Forecasting transportation network speed using deep capsule networks with nested LSTM models publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2020.2984813 – volume: 18 start-page: 621 issue: 3 year: 2017 ident: 10.1016/j.jag.2022.102677_b0155 article-title: Multiple lane detection algorithm based on novel dense vanishing point estimation publication-title: IEEE Trans. Intell. Transport. Syst. doi: 10.1109/TITS.2016.2586187 – volume: 2017 start-page: 2881 year: 2017 ident: 10.1016/j.jag.2022.102677_b0235 article-title: Pyramid scene parsing network publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) – ident: 10.1016/j.jag.2022.102677_b0120 doi: 10.1109/CVPR.2017.106 |
| SSID | ssj0017768 |
| Score | 2.404574 |
| Snippet | •The proposed ACapsFPN extracted road markings in UAV images.•A capsule feature pyramid network provided a high-resolution, semantically-strong feature... Accurately and precisely delineating road-markings from very high spatial resolution unmanned aerial vehicle (UAV) images face many challenges, such as complex... |
| SourceID | doaj proquest crossref elsevier |
| SourceType | Open Website Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 102677 |
| SubjectTerms | Capsule Dense atrous convolution Feature pyramid network neural networks neurons Road markings spatial data UAV images |
| SummonAdditionalLinks | – databaseName: Elsevier SD Freedom Collection Journals [SCFCJ] dbid: AIKHN link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LbxMxELZKe4EDooWK8KiMxAlplV3ba6-PoWqVgugBSNWb5fEj2qrZRGl66L9nvI9AeuiB41q2dzUez3xez3xDyGdfRi3A61Qm1WWChSoDPPRkCNZlUQCvVFvr8MelnM7Et-vyeo-cDrkwKayyt_2dTW-tdd8y7qU5XtX1-BeqJ6IBLljKNsm5eEYOGNcSVftgcvF9erm9TFCqy4grpc4qwdlwudmGed3YOZ4SGUscBlKpHffUsvjveKlH9rp1QuevyMsePdJJ94GHZC80R-TFP5yCR-T47G_qGnbt9-7da3L1c2k9Xdj25zhFm7zuchpo3dDZ5IrWi0Rn8UBTJPycJtrNJplC6iwepG8DjaHlAKWrh7Vd1J42XQD5GzI7P_t9Os36qgqZQ_CxwaWIeQwiSEBsYAP3zHqW6xAiJPCibbRag0Wk4QMDGUF6DQLKisdc4UB-TPabZRPeEiq8C7rkApirBIRCW6urKAuQoYIytyOSD8I0rqccT5Uvbs0QW3ZjUP4myd908h-RL9shq45v46nOX9MKbTsmquy2Ybmem15XDFTRWalBOiXw7BvBgnZC8eBl5bgqRkQM62t2NA-nqp9696dBFwzuyHTNYpuwvL8zDN094wKh77v_m_o9eZ6euki3D2R_s74PHxH6bOCkV-0_-5MCRQ priority: 102 providerName: Elsevier |
| Title | Road marking extraction in UAV imagery using attentive capsule feature pyramid network |
| URI | https://dx.doi.org/10.1016/j.jag.2022.102677 https://www.proquest.com/docview/2718234650 https://doaj.org/article/b8fca69b6c74446fbab9c473ed68c371 |
| Volume | 107 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LTxsxELYQvdADamlRQ1vkSj0hrZrYXq99TBEofSGEGsTN8viBEpENCuHAv-_Y3qXQA71wWmllr63x2PPNeuYbQj77OmoBXqcyqa4SLKgK0OmpEKzL0Qi4anKtw18ncjIV3y_qiwelvlJMWKEHLoL7Aio6KzVI1wh0XSJY0E40PHipHM_Z4wxtXu9MdfcHTVOS4GqpKyU46-8zc2TX3F6iY8hYoi2QTfPIImXi_keG6Z8jOtud41dkuwOMdFwm-ppshHaHvHxAI7hDdo_-Zqth02673rwh52dL6-nC5v_hFI_hVUljoLOWTsfndLZIDBZ3NAW_X9LEtNmm0486i77zVaAxZNpPen23souZp22JGX9LpsdHvw8nVVdIoXKIN9Yo_TiMQQQJCAds4J5Zj0ILIULCK9pGqzVYBBc-MEAZS69BQK14HDbYke-SzXbZhneECu-CrrkA5pSAMNLWahXlCGRQUA_tgAx7YRrXsYynYhdXpg8nmxuUv0nyN0X-A3Jw3-W6UGw81fhrWqH7hokdO79AnTGdzpj_6cyAiH59TQc0CoDAT82eGvtTrwsGN2G6WbFtWN7eGIYWnnGBaHfvOeb3nmylYUuo2weyuV7dho-IfdawT16MD89-nqbntx-Tk_2s9n8AowwFYw |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07b9swED6kztB2KNq0Qd0nC3QqIFgiKUoc3SCB0yQe2jjIRvBpKIhlw3GG_Pse9XDrDhm6UiQlHI93H8W77wC-ujxIbpyMZVJtwqkvE4OHngTBusgyw8qiqXV4MRWTGf9xnV_vwVGfCxPDKjvb39r0xlp3LaNOmqNVVY1-oXoiGmCcxmyTlPEnsB_ZqfIB7I9PzybT7WVCUbQZcbmQSckZ7S83mzCvGz3HUyKlkcNAFMWOe2pY_He81D_2unFCJy_hRYceybj9wFew5-sDeP4Xp-ABHB7_SV3Drt3evXsNVz-X2pGFbn6OE7TJ6zangVQ1mY2vSLWIdBYPJEbCz0mk3ayjKSRW40H61pPgGw5QsnpY60XlSN0GkL-B2cnx5dEk6aoqJBbBxwaXIqTBcy8MYgPtmaPa0VR6H0wEL1IHLaXRiDScp0YEI5w03OQlC2mBA9khDOpl7d8C4c56mTNuqC258ZnUWpZBZEb40uSpHkLaC1PZjnI8Vr64VX1s2Y1C-asof9XKfwjftkNWLd_GY52_xxXadoxU2U3Dcj1Xna4oUwarhTTCFhzPvsFoIy0vmHeitKzIhsD79VU7modTVY-9-0uvCwp3ZLxm0bVf3t8piu6eMo7Q993_Tf0Znk4uL87V-en07D08i0_aqLcPMNis7_1HhEEb86lT898rRQUr |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Road+marking+extraction+in+UAV+imagery+using+attentive+capsule+feature+pyramid+network&rft.jtitle=International+journal+of+applied+earth+observation+and+geoinformation&rft.au=Haiyan+Guan&rft.au=Xiangda+Lei&rft.au=Yongtao+Yu&rft.au=Haohao+Zhao&rft.date=2022-03-01&rft.pub=Elsevier&rft.issn=1569-8432&rft.volume=107&rft.spage=102677&rft_id=info:doi/10.1016%2Fj.jag.2022.102677&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_b8fca69b6c74446fbab9c473ed68c371 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1569-8432&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1569-8432&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1569-8432&client=summon |